Data Transfer

ALCF systems connect to other research institutions using a total of 100 Gbit/s of public network connectivity. This allows scientists to transfer datasets to and from other institutions over fast research networks, such as the Energy Science Network (ESNet) and the Metropolitan Research and Education Network (MREN).

Data Transfer Node Overview

A total of 14 data transfer nodes (DTNs) are available to ALCF users (12 for Mira, one for Vesta, and one for Theta), allowing users to perform wide and local area data transfers. Access to the DTNs is provided via the following virtual endpoints (load balanced via DNS):

Theta: thetadtn.alcf.anl.gov
Mira: miradtn.alcf.anl.gov
Vesta: vestadtn.alcf.anl.gov

The DTNs are individually addressed as dtn01.alcf.anl.gov through dtn12.alcf.anl.gov (Mira), dtn13.alcf.anl.gov (Vesta), and thetadtn01.alcf.anl.gov (Theta), but for load-balancing purposes it is preferable to use the miradtn, vestadtn, and thetadtn endpoints for all transfers. Mira DTNs are configured in stripe groups of four servers, so an individual striped file transfer will use no more than four DTNs at once. The Vesta and Theta DTNs use a single-server setup without striping.

Data Transfer Services and Utilities

Globus

Globus is an easy-to-use interface to GridFTP that addresses the challenges faced by researchers when moving, sharing, and archiving large volumes of data among distributed sites. It is the preferred way to move data with GridFTP, due to its ease of use and ability to automate batch transfers. For more information and instructions:

GridFTP

GridFTP is the underlying transfer protocol that enables large-scale data transfer between such trusted sites as NERSC and ORNL, as well as local nodes at ALCF. The simplest way to use GridFTP is to use the Globus Web service, as described above. However, if you prefer to use the Globus Toolkit for your transfers, or wish to do striped file transfers, you may also use GridFTP directly by using globus-url-copy.

SFTP and SCP

These standard utilities are available for local area transfers of small files; they are not recommended for use with large data transfers due to poor performance and excess resource utilization on the login nodes.

HSI and HTAR

HSI and HTAR allow users to transfer data to and from HPSS locally on ALCF login nodes.